scispace - formally typeset
Search or ask a question

Showing papers on "Crossover published in 1991"


Book ChapterDOI
Larry Eshelman1
01 Jan 1991
TL;DR: CHC is described and analyzed, a nontraditional genetic algorithm which combines a conservative selection strategy that always preserves the best individuals found so far with a radical (highly disruptive) recombination operator that produces offspring that are maximally different from both parents.
Abstract: This paper describes and analyzes CHC, a nontraditional genetic algorithm which combines a conservative selection strategy that always preserves the best individuals found so far with a radical (highly disruptive) recombination operator that produces offspring that are maximally different from both parents The traditional reasons for preferring a recombination operator with a low probability of disrupting schemata may not hold when such a conservative selection strategy is used On the contrary, certain highly disruptive crossover operators provide more effective search Empirical evidence is provided to support these claims

1,152 citations


Book ChapterDOI
01 Jan 1991
TL;DR: It is shown that k-point crossover can be viewed as a crossover operation on the vector of parameters plus perturbations of some of the parameters, which suggests a genetic algorithm that uses real parameter vectors as chromosomes, real parameters as genes, and real numbers as alleles.
Abstract: This paper is concerned with the application of genetic algorithms to optimization problems over several real parameters. It is shown that k-point crossover (for k small relative to the number of parameter) can be viewed as a crossover operation on the vector of parameters plus perturbations of some of the parameters. Mutation can also be considered as a perturbation of some of the parameters. This suggests a genetic algorithm that uses real parameter vectors as chromosomes, real parameters as genes, and real numbers as alleles. Such an algorithm is proposed with two possible crossover methods. Schemata are defined for this algorithm, and it is shown that Holland's Schema theorem holds for one of these crossover methods. Experimental results are given that indicate that this algorithm with a mixture of the two crossover methods outperformed the binary-coded genetic algorithm on 7 of 9 test problems.

1,036 citations


Journal ArticleDOI
TL;DR: In this paper, the applicability of genetic algorithms to the inversion of plane-wave seismograms was investigated, where a random walk in model space and a transition probability rule were used to help guide their search.
Abstract: Seismic waveform inversion is one of many geophysical problems which can be identified as a nonlinear multiparameter optimization problem. Methods based on local linearization fail if the starting model is too far from the true model. We have investigated the applicability of “Genetic Algorithms” (GA) to the inversion of plane‐wave seismograms. Like simulated annealing, genetic algorithms use a random walk in model space and a transition probability rule to help guide their search. However, unlike a single simulated annealing run, the genetic algorithms search from a randomly chosen population of models (strings) and work with a binary coding of the model parameter set. Unlike a pure random search, such as in a “Monte Carlo” method, the search used in genetic algorithms is not directionless. Genetic algorithms essentially consist of three operations, selection, crossover, and mutation, which involve random number generation, string copies, and some partial string exchanges. The choice of the initial popul...

378 citations


Book ChapterDOI
01 Jan 1991
TL;DR: This work investigates the PGA with deceptive problems and the traveling salesman problem, a parallel search with information exchange between the individuals, and shows the correlation for thetraveling salesman problem by a configuration space analysis.
Abstract: The parallel genetic algorithm (PGA) uses two major modifications compared to the genetic algorithm. Firstly, selection for mating is distributed. Individuals live in a 2-D world. Selection of a mate is done by each individual independently in its neighborhood. Secondly, each individual may improve its fitness during its lifetime by e.g. local hill-climbing. The PGA is totally asynchronous, running with maximal efficiency on MIMD parallel computers. The search strategy of the PGA is based on a small number of active and intelligent individuals, whereas a GA uses a large population of passive individuals. We will investigate the PGA with deceptive problems and the traveling salesman problem. We outline why and when the PGA is succesful. Abstractly, a PGA is a parallel search with information exchange between the individuals. If we represent the optimization problem as a fitness landscape in a certain configuration space, we see, that a PGA tries to jump from two local minima to a third, still better local minima, by using the crossover operator. This jump is (probabilistically) successful, if the fitness landscape has a certain correlation. We show the correlation for the traveling salesman problem by a configuration space analysis. The PGA explores implicitly the above correlation.

357 citations


Patent
05 Nov 1991
TL;DR: In this article, a non-linear genetic algorithm for problem solving is presented, which is useful for solving at least three groups of problems, namely, symbolic function identification, symbolic regression, empirical discovery, modeling, induction, chaos, and forecasting.
Abstract: The present invention is a non-linear genetic algorithm for problem solving. The iterative process of the present invention operates on a population of problem solving entities. First, the activated entities perform producing results. Then the results are assigned values and associated with the producing entity. Next, entities having relatively high associated values are selected. The selected entities perform either crossover or fitness proportionate reproduction. In addition other operations such as mutation, permutation, define building blocks and editing may be used. Lastly, the newly created entities are added to the population. This invention disclosed herein is useful for solving at least three groups of problems. The first group of problems consists of a problem that presents itself under several different names, namely, the problem of symbolic function identification, symbolic regression, empirical discovery, modeling, induction, chaos, and forecasting. The second group of problems contains several similar, but different, problems. This group contains the problems of symbolic integration, symbolic differentiation, symbolic solution of differential equations, symbolic solution of integral equations, symbolic solution of mathematical equations, and inverses. The third group of problems contains several other seemingly different, but related, problems, namely, function learning, planning, automatic programming, game playing, concept formulation, pattern recognition, and neural net design. All of these problems can be formulated and then solved in the manner described herein.

242 citations


Journal ArticleDOI
TL;DR: An investigation into the application of the genetic algorithm in the optimization of structural design and the basic operations of selection, crossover, mutation and parameter scaling are presented.

215 citations


Journal ArticleDOI
TL;DR: The actuator location selection problem is cast in the framework of a zero-one optimization problem and a genetic algorithmic approach is developed that involves three basic operations: reproduction, crossover, and mutation.
Abstract: The actuator location selection problem is cast in the framework of a zero-one optimization problem. A genetic algorithmic approach is developed. To obtain successive generations that yield the solution corresponding to the maximum fitness value, this approach involves three basic operations: reproduction, crossover, and mutation.

192 citations


01 Jan 1991
TL;DR: Preliminary computational comparisons with the current best known method for query optimization indicate this to be a promising approach, and the output quality and the time needed to produce such solutions is comparable to and in general better than the current method.
Abstract: Current query optimization techniques are inadequate to support some of the emerging database applications. In this paper, we outline a database query optimization problem and describe the adaptation of a genetic algorithm to the problem. We present a method for encoding arbitrary binary trees as chromosomes and describe several crossover operators for such chromosomes. Preliminary computational comparisons with the current best{known method for query optimization indicate this to be a promising approach. In particular, the output quality and the time needed to produce such solutions is comparable to and in general better than the current method.

144 citations



Book ChapterDOI
16 Oct 1991
TL;DR: This report re-examines these studies, and concludes that the results were caused by a small population size, and indicates that better neural networks can be evolved in a shorter time if the genetic algorithm uses crossover.
Abstract: Holland's analysis of the sources of power of genetic algorithms has served as guidance for the applications of genetic algorithms for more than 15 years. The technique of applying a recombination operator (crossover) to a population of individuals is a key to that power. Neverless, there have been a number of contradictory results concerning crossover operators with respect to overall performance. Recently, for example, genetic algorithms were used to design neural network modules and their control circuits. In these studies, a genetic algorithm without crossover outperformed a genetic algorithm with crossover. This report re-examines these studies, and concludes that the results were caused by a small population size. New results are presented that illustrate the effectiveness of crossover when the population size is larger. From a performance view, the results indicate that better neural networks can be evolved in a shorter time if the genetic algorithm uses crossover.

137 citations



Book ChapterDOI
01 Jan 1991
TL;DR: The more disruptive operator, uniform crossover, is more effective at combatting the spurious correlations at the expense of also more disruption of the effective schemata, suggesting that research into ways of dealing with the effects of the inevitable sampling errors may lead to generally more robust algorithms.
Abstract: What distinguishes genetic algorithms (GA) from other search methods is their inherent exploitive sampling ability known as implicit parallelism. We argue, however, that this exploitive behavior makes GAs sensitive to spurious correlations between schemata that contribute to performance and schemata that are parasitic. If not combatted, this can lead to premature convergence. Among crossover operators, some are more disruptive than others, and traditional arguments have held that less disruption is better for implicit parallelism. To explore this issue we examine the behavior of two crossover operators, two-point and uniform crossover, on a problem contrived to contain specific spurious correlations. The more disruptive operator, uniform crossover, is more effective at combatting the spurious correlations at the expense of also more disruption of the effective schemata. Elitist selection procedures are shown to be able to ameliorate this somewhat, suggesting that research into ways of dealing with the effects of the inevitable sampling errors may lead to generally more robust algorithms.

Journal ArticleDOI
TL;DR: In this article, the authors investigate a random effects model and show that the model is simple and general, and interpretation of parameters is easy, though with a complicated fitting procedure.
Abstract: Crossover studies have been successfully conducted in the case of continuous responses. Existing procedures of analysis for ordinal responses, on the other hand, are rarely satisfactory unless strict, usually unrealistic, assumptions are made. In this paper we investigate a random effects model and show that the model is simple and general. Interpretation of parameters is easy, though with a complicated fitting procedure.

Journal Article
TL;DR: A genetic algorit hm with a new crossover operator called block-uniform crossover, which exploits the two-dimensional character of a problem and outperforms genetic algorithms with traditional crossover operators in all tri als.
Abstract: The genetic algorithm is a powerful heuristic for the solution of hard combinatorial problems and has been investigated by numer ous authors. Many problems, arising for example in communi. cation networks, possess stro ng two-dimensional characteristics. We describe a genetic algorit hm with a new crossover operator called block-uniform crossover, which exploits the two-dimensional character of a problem. Th e concept was tested on a version of the Ising model, which is important in physics. Thi s new algorit hm outperforms genetic algorithms with traditional crossover operators in all tri als.

Journal ArticleDOI
TL;DR: The genetic algorithm has been applied to the VLSI module placement problem, and it is pointed out that the bitmap representation enables the algorithm to divide the entire solution space into a set of feature-equivalent classes, or schemata where each class contains aSet of solutions with common physical attributes.

Journal ArticleDOI
TL;DR: The methodology leads to the use of median survival times to illustrate treatment effects and this provides a practical interpretation of clinical relevance and the estimation of Median survival times in crossover trials poses some special problems.
Abstract: Clinical trials of new drugs in the treatment of angina pectoris frequently make use of exercise tests to evaluate efficacy. The crossover design is often employed. The methods commonly used to analyse the various exercise times, for example, 'time to pain', are insensitive and potentially biased by the manner in which they deal with the censored nature of the data. Survival analysis can be adapted for use in crossover trials, both in a relatively simple way, and also through the full power of the Cox model. This is considerably more sensitive and not subject to the same bias. This methodology leads to the use of median survival times to illustrate treatment effects and this provides a practical interpretation of clinical relevance. The estimation of median survival times in crossover trials poses some special problems. The methodology is illustrated throughout by means of a specific two-period example in which atenolol was compared with the combination of atenolol and nifedipine. The three-period design is also briefly discussed.

Journal ArticleDOI
TL;DR: This paper indicates how the usual crossover test has to be interpreted correctly and that its bias has two different consequences, namely a conservative or a liberal test decision if a positive (carryover) or a negative (withdrawal) residual effect exists.
Abstract: When a residual effect is suspected in a two-period crossover trial, an analysis of the first-period data is often chosen instead of the potentially biased crossover analysis. This paper indicates how the usual crossover test has to be interpreted correctly and that its bias has two different consequences, namely a conservative or a liberal test decision if a positive (carryover) or a negative (withdrawal) residual effect exists. A multiple testing procedure is presented allowing for simultaneous crossover and first-period analysis controlling the experimental error rate. This procedure together with the correct interpretation of the crossover test enables many useful applications of crossover designs.


Journal ArticleDOI
TL;DR: The simple two-treatment, two-period crossover trial provides an efficient way of comparing the efficacies of two treatments for the short-term alleviation of a chronic condition.
Abstract: The simple two-treatment, two-period crossover trial is under attack again. In ideal circumstances this design provides an efficient way of comparing the efficacies of two treatments for the short-term alleviation of a chronic condition

Journal ArticleDOI
TL;DR: Optical implementations of both 2-D and 3-D crossover networks are described, and it is shown that these networks can be used for connecting multiple stages of 2-input, 2-output switching elements.
Abstract: Optical implementations of both 2-D and 3-D crossover networks are described, and we show that these networks can be used for connecting multiple stages of 2-input, 2-output switching elements. We also show that simple conversion steps can be used to convert 2-D crossover networks into 3-D crossover networks. Both network types can be implemented with low loss optical imaging systems, and we show that the same optics can be used to implement the intranode connections and the internode for various types of 2-input, 2-output switching elements. In addition, we discuss the difficulties that arise when the same optical hardware is applied to switching elements of larger dimensionality.

Journal ArticleDOI
Stephen Senn1, H. Hildebrand1
TL;DR: It is suggested that the phenomenon of patient by treatment interaction requires a repeated measures approach to the analysis of crossover trials and a simple solution using predefined contrasts is presented.
Abstract: The problem of carryover in crossover trials has received a great deal of attention in the statistical literature. Carryover is just one form of period by treatment interaction; yet a parallel problem of patient by treatment interaction, which may be regarded as dual to that of carryover, has received little attention. We suggest that the phenomenon of patient by treatment interaction requires a repeated measures approach to the analysis of crossover trials. A simple solution using predefined contrasts is presented and illustrated by example.

Book ChapterDOI
01 Jan 1991
TL;DR: A reformulation of the genetic algorithm is proposed that makes it appropriate to any representation that can be cast in a formal grammar, and concentrates on the modifications required to make the space of legal structures closed under the crossover operator.
Abstract: High-level syntactically-based representations pose problems for applying the GA because it is hard to construct crossover operators that always result in legal offspring. This paper proposes a reformulation of the genetic algorithm that makes it appropriate to any representation that can be cast in a formal grammar. This reformulation is consistent with recent reinterpretations of GA foundations in set-theoretic terms, and concentrates on the modifications required to make the space of legal structures closed under the crossover operator. The analysis places no restriction on the form of the grammars.

Proceedings ArticleDOI
03 Nov 1991
TL;DR: The authors attempt to realize a mechanism in which the 3D packing rule is automatically tuned, and an optimum packing solution is obtained by applying genetic algorithms which mimic the process of a natural evolution system.
Abstract: A new approach of how to solve the 3D packing problem automatically is proposed. This problem is well known as a complete combinatorial problem. The authors attempt to realize a mechanism in which the 3D packing rule is automatically tuned, and an optimum packing solution is obtained by applying genetic algorithms which mimic the process of a natural evolution system. The 3D packing strategy is controlled by two evaluation functions which dominate the selection of a next allocation position and a box. To find the near-optimal strategy, the weighted coefficients of the evaluation functions are tuned by applying the genetic operators such as reproduction, crossover and mutation. To use the obtained tuned results as accumulated successful strategies, a 3D packing rule-base is constructed. The rules in this rule-base are composed of a 'conditional part', which expresses the features of the given problem, and a 'procedural part', which gives the packing strategy. >


Proceedings ArticleDOI
10 Nov 1991
TL;DR: Two new crossover operators in genetic algorithms for solving some combinatorial problems with ordering are presented, including enhanced order crossover (EOX) and GREE, a heuristic crossover for a class of combinatorsial optimization problems, such as traveling salesman problems (TSPs).
Abstract: Two new crossover operators in genetic algorithms for solving some combinatorial problems with ordering are presented. One is enhanced order crossover (EOX). The other, GREE, is a heuristic crossover for a class of combinatorial optimization problems, such as traveling salesman problems (TSPs). Genetic algorithms using GREE as unique crossover run very fast and get good solutions. Combining GREE with EOX, genetic algorithms can find optimal or very near optimal solutions in a rather short time. >

Journal Article
TL;DR: In this paper, a Message-Based Bucket Brigade (MBB) algorithm is proposed, in which messages instead of rules are evaluated and a rule quality is then a function of the value of the messages matching the rule conditions, of the rule condition specificity and of the message the rule tries to post.
Abstract: This paper considers some issues related to the apportionment of credit problem in Genetic Based Machine Learning systems (GBML). A GBML system is composed of three major subsystems. The first one, the performance subsystem, is a parallel adaptive rule-based system where the knowledge base is a set of rules expressed in a low-level syntax. The second subsystem, called Genetic Algorithm (GA), is a procedure that searches in the rule space by means of genetic operators modelled according to natural genetic operators (e.g. reproduction, crossover, mutation). The third subsystem faces the apportionment of credit problem, i.e. how to evaluate the quality of existing rules. In this paper we propose an apportionment of credit algorithm, called Message-Based Bucket Brigade, in which messages instead of rules are evaluated. A rule quality is then a function of the value of the messages matching the rule conditions, of the rule conditions specificity and of the value of the message the rule tries to post. This approach gives a solution to the default hierarchy formation problem, i.e. the problem of creating set of rules in which default rules cover broad categories of system responses, while specific ones cover situations in which default rules are incorrect. A comparison with other approaches to default hierarchy formation is presented. The final section presents conclusions and suggests directions for further research.

Journal ArticleDOI
TL;DR: A general homogeneity relation for the noise of both insulators and conductors is suggested and the expression for the total noise is valid from the noisy-cond conductor quiet-insulator limit to the quiet-conductor noisy-insulators limit.
Abstract: The resistance noise of random conductor-insulator mixtures is studied in the case where the insulator has a small, but finite conductivity. Based on the structure of a simple renormalization group, a general homogeneity relation for the noise of both insulators and conductors is suggested. The expression for the total noise is valid from the noisy-conductor quiet-insulator limit to the quiet-conductor noisy-insulator limit. Monte Carlo simulations confirm the scaling predictions. For all multifractal moments, there is a single crossover exponent associated with the small finite conductivity of the insulator.

Journal ArticleDOI
TL;DR: A discussion of the basic theory of genetic algorithms is presented and a genetic algorithm solution of a lumber cutting optimization problem is presented.
Abstract: Genetic algorithms are a technique for search and optimization based on the Darwinian principle of natural selection. They are iterative search procedures that maintain a population of candidate solutions. The best or most fit solutions in that population are then used as the basis for the next generation of solutions. The next generation is formed using the genetic operators reproduction, crossover, and mutation. Genetic algorithms have been successfully applied to engineering search and optimization problems. This paper presents a discussion of the basic theory of genetic algorithms and presents a genetic algorithm solution of a lumber cutting optimization problem. Dimensional lumber is assigned a grade that represents its physical properties. A grade is assigned to every board segment of a specific length. The board is then cut in various locations in order to maximize its value, A genetic algorithm was used to determine the cutting patterns that would maximize the board value.

Journal ArticleDOI
C. Dekker1, Roger H. Koch1, B. Oh1, Ayush Gupta1
TL;DR: The IV characteristics of thin YBa2Cu3O7−δ films show a crossover from the critical scaling behavior of the intrinsic three-dimensional (3D) transition, observed at high currents, to an ohmic resistance at low currents associated with a two-dimensional phase.
Abstract: The IV characteristics of thin (250–4000 A) YBa2Cu3O7−δ films show a crossover from the critical scaling behavior of the intrinsic three-dimensional (3D) transition, observed at high currents, to an ohmic resistance at low currents associated with a two-dimensional phase. This crossover is observed near the 3D phase transition from normal to vortex-glass phase in a high magnetic field, as well as for H = 0 near the transition into the Meissner phase. The crossover occurs when the growth of the 3D correlation length, ξθ(T − Tc,3D)−v, is limited by the film thickness.

Book ChapterDOI
01 Jan 1991
TL;DR: In this paper, a standard case of Strong Crossover (SC) is defined: "Whoi does hei love ti?" and the answer is "whoi does ti love ti?
Abstract: Example (1) illustrates a standard case of Strong Crossover (SC): (1) *Whoi does hei love ti?